Hugging Face's logo

OpenFinAL
/
FINGPT_QA_V2

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Model card Files
xet
Community
Divy0409 commited on
Commit
77674b2
·
verified ·
1 Parent(s): 6d5ce70

Upload OpenELMForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +81 -31
  2. generation_config.json +2 -2
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,39 +1,89 @@
1
  {
2
- "_name_or_path": "gpt2",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.1,
10
- "eos_token_id": 50256,
11
- "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 12,
19
- "n_positions": 1024,
20
- "reorder_and_upcast_attn": false,
21
- "resid_pdrop": 0.1,
22
- "scale_attn_by_inverse_layer_idx": false,
23
- "scale_attn_weights": true,
24
- "summary_activation": null,
25
- "summary_first_dropout": 0.1,
26
- "summary_proj_to_labels": true,
27
- "summary_type": "cls_index",
28
- "summary_use_proj": true,
29
- "task_specific_params": {
30
- "text-generation": {
31
- "do_sample": true,
32
- "max_length": 50
33
- }
34
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.46.3",
37
  "use_cache": true,
38
- "vocab_size": 50257
39
  }
 
1
  {
2
+ "_name_or_path": "apple/OpenELM-270M-Instruct",
3
+ "activation_fn_name": "swish",
4
  "architectures": [
5
+ "OpenELMForCausalLM"
6
  ],
7
+ "auto_map": {
8
+ "AutoConfig": "apple/OpenELM-270M-Instruct--configuration_openelm.OpenELMConfig",
9
+ "AutoModelForCausalLM": "apple/OpenELM-270M-Instruct--modeling_openelm.OpenELMForCausalLM"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "ffn_dim_divisor": 256,
14
+ "ffn_multipliers": [
15
+ 0.5,
16
+ 0.73,
17
+ 0.97,
18
+ 1.2,
19
+ 1.43,
20
+ 1.67,
21
+ 1.9,
22
+ 2.13,
23
+ 2.37,
24
+ 2.6,
25
+ 2.83,
26
+ 3.07,
27
+ 3.3,
28
+ 3.53,
29
+ 3.77,
30
+ 4.0
31
+ ],
32
+ "ffn_with_glu": true,
33
+ "head_dim": 64,
34
+ "initializer_range": 0.02,
35
+ "max_context_length": 2048,
36
+ "model_dim": 1280,
37
+ "model_type": "openelm",
38
+ "normalization_layer_name": "rms_norm",
39
+ "normalize_qk_projections": true,
40
+ "num_gqa_groups": 4,
41
+ "num_kv_heads": [
42
+ 3,
43
+ 3,
44
+ 3,
45
+ 3,
46
+ 3,
47
+ 4,
48
+ 4,
49
+ 4,
50
+ 4,
51
+ 4,
52
+ 4,
53
+ 4,
54
+ 5,
55
+ 5,
56
+ 5,
57
+ 5
58
+ ],
59
+ "num_query_heads": [
60
+ 12,
61
+ 12,
62
+ 12,
63
+ 12,
64
+ 12,
65
+ 16,
66
+ 16,
67
+ 16,
68
+ 16,
69
+ 16,
70
+ 16,
71
+ 16,
72
+ 20,
73
+ 20,
74
+ 20,
75
+ 20
76
+ ],
77
+ "num_transformer_layers": 16,
78
+ "qkv_multipliers": [
79
+ 0.5,
80
+ 1.0
81
+ ],
82
+ "rope_freq_constant": 10000,
83
+ "rope_max_length": 4096,
84
+ "share_input_output_layers": true,
85
  "torch_dtype": "float32",
86
  "transformers_version": "4.46.3",
87
  "use_cache": true,
88
+ "vocab_size": 32000
89
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
  "transformers_version": "4.46.3"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
  "transformers_version": "4.46.3"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a257704789f27c1fe4658daae85df852f300f1c042e51e7d856bd255eec0521
3
- size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3533b6637933eac2477a105ca5c63885c1f36b97efb0013c28d04ea5efdfd1c4
3
+ size 1086123184